Implementing ML/DL papers

• Here I will be trying to implement research papers, machine learning and deep learning concepts.
• The goal is to build a deeper understanding of the theory behind ML/DL

Activation Functions:

• ReLU
• Leaky ReLU
• ELU
• SELU
• GELU
• Swish
• Sigmoid
• Tanh
• Softmax

Loss Functions:

• Mean Squared Error (MSE)
• Log Loss / Binary Cross Entropy

Deep Learning:

• Conv1D
• Vanilla RNN Cell
• Conv2D

Linear Algebra & Core Ops:

• Dot Product
• Outer Product
• Element-wise Multiplication (Pure Python + NumPy validation)
• Matrix Multiplication (with and without NumPy)

Building Blocks of Transformer Architecture

• Self-Attention
• Scaled Dot-Product Attention
• Masked Attention
• Multi-Head Attention